GOLFS: Feature Selection via Combining Both Global and Local Information for High Dimensional Clustering

TL;DR

GOLFS is an unsupervised feature selection method that combines local geometric and global correlation information to improve high dimensional clustering accuracy.

Contribution

The paper introduces GOLFS, a novel unsupervised feature selection approach that integrates manifold learning and self-representation for better clustering in high dimensions.

Findings

GOLFS outperforms existing methods in feature selection accuracy.

GOLFS achieves superior clustering results on real datasets.

The iterative algorithm converges reliably.

Abstract

It is important to identify the discriminative features for high dimensional clustering. However, due to the lack of cluster labels, the regularization methods developed for supervised feature selection can not be directly applied. To learn the pseudo labels and select the discriminative features simultaneously, we propose a new unsupervised feature selection method, named GlObal and Local information combined Feature Selection (GOLFS), for high dimensional clustering problems. The GOLFS algorithm combines both local geometric structure via manifold learning and global correlation structure of samples via regularized self-representation to select the discriminative features. The combination improves the accuracy of both feature selection and clustering by exploiting more comprehensive information. In addition, an iterative algorithm is proposed to solve the optimization problem and the convergency is proved. Simulations and two real data applications demonstrate the excellent finite-sample performance of GOLFS on both feature selection and clustering.